Behavioral plasticity through the modulation of switch neurons.

A central question in artificial intelligence is how to design agents capable of switching between different behaviors in response to environmental changes. Taking inspiration from neuroscience, we address this problem by utilizing artificial neural networks (NNs) as agent controllers, and mechanisms such as neuromodulation and synaptic gating. The novel aspect of this work is the introduction of a type of artificial neuron we call "switch neuron".

Toward nonlinear local reinforcement learning rules through neuroevolution.

We consider the problem of designing local reinforcement learning rules for artificial neural network (ANN) controllers. Motivated by the universal approximation properties of ANNs, we adopt an ANN representation for the learning rules, which are optimized using evolutionary algorithms. We evaluate the ANN rules in partially observable versions of four tasks: the mountain car, the acrobot, the cart pole balancing, and the nonstationary mountain car.

A comparative study on filtering protein secondary structure prediction.

Filtering of Protein Secondary Structure Prediction (PSSP) aims to provide physicochemically realistic results, while it usually improves the predictive performance. We performed a comparative study on this challenging problem, utilizing both machine learning techniques and empirical rules and we found that combinations of the two lead to the highest improvement.

Multiagent reinforcement learning: spiking and nonspiking agents in the iterated Prisoner's Dilemma.

This paper investigates multiagent reinforcement learning (MARL) in a general-sum game where the payoffs' structure is such that the agents are required to exploit each other in a way that benefits all agents. The contradictory nature of these games makes their study in multiagent systems quite challenging. In particular, we investigate MARL with spiking and nonspiking agents in the Iterated Prisoner's Dilemma by exploring the conditions required to enhance its cooperative outcome.

Perceptual distance and the moon illusion.

The elevated moon usually appears smaller than the horizon moon of equal angular size. This is the moon illusion. Distance cues may enable the perceptual system to place the horizon moon at an effectively greater distance than the elevated moon, thus making it appear as larger.

Hepatic arterial resistive indices: correlation with the severity of cirrhosis.

Forty-three patients who were scheduled to undergo a percutaneous liver biopsy were evaluated with Doppler sonography to determine the hepatic arterial resistive index (RI). The histologic specimens were graded by a pathologist regarding cirrhosis and inflammation. The specimens demonstrated no cirrhosis in 12 of 43 (28%) patients, early cirrhosis in 10 of 43 (23%), and established cirrhosis in 21 of 43 (49%).

Focal and diffuse benign hepatic disease: correlative imaging.

With the large numbers of screening CT scans and ultrasounds performed in a busy radiologic practice, it is not uncommon to discover an unexpected focal or diffuse process in the liver. When there is no history of primary malignancy, many of these lesions are benign. We discuss the variety of benign focal and diffuse diseases that can be readily imaged within the liver using ultrasound, CT, and MR.

Percutaneous renal and adrenal biopsies.

With today's imaging technology, relatively invasive procedures can be performed in the radiology department without significant complication. Biopsies, in particular, are frequently performed using computed tomography (CT) or ultrasound (US) guidance. In this article, both the indications and methods for imaging-guided percutaneous biopsy of the kidney and adrenal gland are reviewed.

Hepatic metastases: CT versus MR imaging at 1.5T.

A prospective multi-institutional study was performed to compare the sensitivity of computed tomography (CT) and high-field magnetic resonance (MR) imaging (1.5T) in the detection of hepatic metastases. T1-weighted and 72-weighted spin-echo (SE) MR images were compared with noncontrast, dynamic, and delayed CT.

Magnetic resonance imaging of the liver.

Hepatic MRI has become a useful imaging modality in recent years. As with all diagnostic imaging, the scanning techniques available for hepatic MRI are manifold and complex. The article discusses these techniques and their practical applications.